fix(mongodb): reject dict filter values to prevent NoSQL operator injection (#5748)

mem0/vector_stores/mongodb.py

@@ -148,6 +148,22 @@ class MongoDB(VectorStoreBase):
         except PyMongoError as e:
             logger.error(f"Error inserting data: {e}")
 
+    @staticmethod
+    def _validate_filter_value(key: str, value: Any) -> None:
+        """Reject values that could inject MongoDB query operators (e.g. $ne, $gt)."""
+        if isinstance(value, dict):
+            raise ValueError(
+                f"Filter value for {key!r} must be a scalar (str, int, float, bool), "
+                f"not a dict. Dicts may contain MongoDB query operators."
+            )
+        if isinstance(value, list):
+            for item in value:
+                if isinstance(item, dict):
+                    raise ValueError(
+                        f"Filter list for {key!r} contains a dict, "
+                        f"which may contain MongoDB query operators."
+                    )
+
     def search(self, query: str, vectors: List[float], top_k=5, filters: Optional[Dict] = None) -> List[OutputData]:
         """
         Search for similar vectors using the vector search index.
@@ -167,6 +183,10 @@ class MongoDB(VectorStoreBase):
             logger.error(f"Index '{self.index_name}' does not exist.")
             return []
 
+        if filters:
+            for key, value in filters.items():
+                self._validate_filter_value(key, value)
+
         results = []
         try:
             collection = self.client[self.db_name][self.collection_name]
@@ -215,6 +235,9 @@ class MongoDB(VectorStoreBase):
         Returns:
             List[OutputData]: Search results, or None if Atlas Search index is not available.
         """
+        if filters:
+            for key, value in filters.items():
+                self._validate_filter_value(key, value)
         try:
             collection = self.client[self.db_name][self.collection_name]
             search_index_name = f"{self.collection_name}_text_search_index"
@@ -369,6 +392,9 @@ class MongoDB(VectorStoreBase):
         Returns:
             List[OutputData]: List of vectors.
         """
+        if filters:
+            for key, value in filters.items():
+                self._validate_filter_value(key, value)
         try:
             query = {}
             if filters:

tests/vector_stores/test_mongodb.py

@@ -401,3 +401,29 @@ def test_list_with_no_filters(mongo_vector_fixture):
 
     assert len(results) == 1
     assert len(results[0]) == 1
+
+
+def test_search_rejects_operator_injection(mongo_vector_fixture):
+    """Filter values containing MongoDB operators (dicts) must be rejected."""
+    mongo_vector, mock_collection, _ = mongo_vector_fixture
+    mock_collection.list_search_indexes.return_value = ["test_collection_vector_index"]
+
+    with pytest.raises(ValueError, match="not a dict"):
+        mongo_vector.search("q", [0.1] * 1536, top_k=2, filters={"user_id": {"$ne": ""}})
+
+
+def test_list_rejects_operator_injection(mongo_vector_fixture):
+    """list() must also reject MongoDB operator injection."""
+    mongo_vector, _, _ = mongo_vector_fixture
+
+    with pytest.raises(ValueError, match="not a dict"):
+        mongo_vector.list(filters={"user_id": {"$regex": ".*"}})
+
+
+def test_search_allows_scalar_filter_values(mongo_vector_fixture):
+    """Normal scalar filter values (str, int, bool) must still work."""
+    mongo_vector, mock_collection, _ = mongo_vector_fixture
+    mock_collection.aggregate.return_value = []
+    mock_collection.list_search_indexes.return_value = ["test_collection_vector_index"]
+
+    mongo_vector.search("q", [0.1] * 1536, top_k=2, filters={"user_id": "alice", "count": 5})